Papers by Andrea Pierleoni
WebIE: Faithful and Robust Information Extraction on the Web (2023.acl-long)
Copied to clipboard
| Challenge: | Existing closed IE datasets are built using Wikipedia, but they have limitations when applied to web domains. |
| Approach: | They propose to annotate 25K triples from WebIE through crowdsourcing and introduce mWebIE, a translation of the annotated set in four other languages. |
| Outcome: | The proposed model trains on 1.6M sentences from the English Common Crawl corpus and includes negative examples to better reflect the data on the web. |
Reasoning Over Paths via Knowledge Base Completion (D19-53)
Copied to clipboard
| Challenge: | Existing methods to predict missing links in knowledge graphs are lacking. |
| Approach: | They propose a method to automatically rank paths between a source and target entity pair using a knowledge base completion model. |
| Outcome: | The proposed method can rank and rank paths in biomedical knowledge graphs with a KBC model. |
ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linking (2022.naacl-industry)
Copied to clipboard
| Challenge: | Entity linking is the task of recognising mentions of entities in unstructured text documents and linking them to the corresponding entities in a Knowledge Base (KB) the largest public EL dataset is Wikipedia, which covers just 3% of the entities in Wikidata. |
| Approach: | They propose a model which performs mention detection, fine-grained entity typing, and entity disambiguation for all mentions within a document in a single forward pass. |
| Outcome: | The proposed model outperforms state-of-the-art methods on standard datasets by an average of 3.7 F1 and can generalise to large-scale knowledge bases such as Wikidata and zero-shot entity linking. |
HALLUCANA: Fixing LLM Hallucination with A Canary Lookahead (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods to detect factual hallucinations w.r.t. world knowledge require assistive generations (samples, drafts, etc.) Existing approaches to factuality hallucinism detection, such as SelfCheckGPT, require assistively generation (sequences, Drafts, and etc.). Existing studies on factualism hallucinosation detection require assistives generations (Sample, draft, etc). |
| Approach: | They propose a canary lookahead which detects and corrects factual hallucinations of Large Language Models in long-form generation by exploiting the internal factuality representation in the LLM hidden space. |
| Outcome: | The proposed method improves generation quality by 2.5x while consuming over 6 times less compute. |
Improving Entity Disambiguation by Reasoning over a Knowledge Base (2022.naacl-main)
Copied to clipboard
| Challenge: | Recent work in entity disambiguation relies on a limited subset of KB facts to link entities . less common entities are prone to missing or inconsistent KB information, which is problematic for models which rely on 'one source' |
| Approach: | They propose an ED model which links entities by reasoning over a symbolic knowledge base in a fully differentiable fashion. |
| Outcome: | The proposed model outperforms state-of-the-art models on six well-established datasets by 1.3 F1 on average. |
Deep Bidirectional Transformers for Relation Extraction without Supervision (D19-61)
Copied to clipboard
| Challenge: | Existing frameworks for relation extraction use distant supervision instead of annotated data. |
| Approach: | They propose a framework to deal with relation extraction tasks without supervision . they use syntactic parsing and pre-trained word embeddings to extract relations . |
| Outcome: | The proposed framework outperforms baselines on four biomedical datasets and achieves slightly worse results than the state-of-the-art in three out of four data sets. |